点云
计算机科学
人工智能
最小边界框
跳跃式监视
RGB颜色模型
计算机视觉
目标检测
图像(数学)
深度学习
激光雷达
对象(语法)
传感器融合
点(几何)
模式识别(心理学)
遥感
地理
数学
几何学
作者
Danfei Xu,Dragomir Anguelov,Ashesh Jain
标识
DOI:10.1109/cvpr.2018.00033
摘要
We present PointFusion, a generic 3D object detection method that leverages both image and 3D point cloud information. Unlike existing methods that either use multistage pipelines or hold sensor and dataset-specific assumptions, PointFusion is conceptually simple and application-agnostic. The image data and the raw point cloud data are independently processed by a CNN and a PointNet architecture, respectively. The resulting outputs are then combined by a novel fusion network, which predicts multiple 3D box hypotheses and their confidences, using the input 3D points as spatial anchors. We evaluate PointFusion on two distinctive datasets: the KITTI dataset that features driving scenes captured with a lidar-camera setup, and the SUN-RGBD dataset that captures indoor environments with RGB-D cameras. Our model is the first one that is able to perform better or on-par with the state-of-the-art on these diverse datasets without any dataset-specific model tuning.
科研通智能强力驱动
Strongly Powered by AbleSci AI